Introduction: COVID-19 is found as an irresistible sickness pandemic that has carried uncommon difficulties to worldwide networks across open and private sectors. Data processing and creating awareness is the important tool that implements the powerful actions to mitigate the spread of covid-19. Objective: To develop a supervised regression algorithm with minimum variance unbiased estimator which could the data on daily basis to assure the safety movement in post-covid-19. Based on the number of infected cases, the data will be trained for better prediction to create awareness for the public in the safety movement. Methods: The proposed supervised regression algorithm was able to model the relationship between the number of cases registered and a continuous target variable. By optimizing the error rate, the training algorithm was fine-tuned and the prediction was able to closely approximate the actual values. The proposed method was compared with other methods like Linear Regression, Logistic Regression and Supporting Vector machine (SVM). Results: Simulation results proved that the proposed supervised regression with minimum variance unbiased estimation provides better prediction when compared to the other methods. Conclusion: An attempt was made to predict the number of cases by a suitable regression algorithm and the prediction was compared with other regression algorithms. The algorithm was able to predict the infections rates and death count with the least error when provided with training data. This data purely depends on the lockdown implementations, movement of people without restrictions and the lack of awareness to face this pandemic situation. In future, the aspects can also be incorporated into the model for a better and accurate prediction.